Search Support Apparatus Question Type Adaptability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search systems fail to provide responses in a mode corresponding to question sentences, making it difficult to display information requested by users, as they only retrieve and display images or blog articles associated with keywords without considering the question type or output pattern.
Innovation Solution
A computer-readable recording medium with a program that receives a question sentence, extracts keywords to specify the question object and type, determines the display mode of the response output based on the question type, and outputs search results accordingly, using a question phrase dictionary and extraction rule information to process and display relevant information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional search systems only retrieve and display images or blog articles associated with keywords, then the search process is simple, but the system cannot return responses in a mode corresponding to the question sentence type
Solution Approach 1:
The system segments the question sentence into distinct components: question type (e.g., what, where, when, who, why, how) and question object (keywords). This segmentation allows the system to process each component separately and apply appropriate response modes for each question type, thereby achieving adaptability without overwhelming complexity.
Solution Approach 2:
The patent introduces an intermediary processing layer that includes a question type determination unit and a question object extraction unit. This intermediary layer translates the user's natural language question into structured data that can be matched with predefined response modes, enabling adaptable responses while maintaining system manageability.
2Measurement precision
If the system extracts and processes multiple types of keywords (question object and question type), then the response accuracy improves, but the information processing complexity increases
Solution Approach 1:
The system divides keyword processing into two distinct segmentation tasks: extracting the question object (what the user wants to know about) and determining the question type (how the question is framed). This segmentation enables precise matching of both components with appropriate search strategies and response formats, improving accuracy while keeping each processing module relatively simple.
Solution Approach 2:
Different processing methods are applied to different parts of the question based on their specific requirements. The question object extraction uses one set of methods (e.g., noun phrase identification), while the question type determination uses another set (e.g., interrogative word recognition). This local quality approach optimizes processing for each component's specific needs.
Data Source
AI summary
A search support apparatus includes a receiving unit, a determining unit, and an output unit. The receiving unit receives a question containing a character string and extracts a keyword for specifying a question object and a keyword for specifying a question type from the character string contained in the question. The determining unit determines a display mode of an output of a response to the received question in accordance with the keyword for specifying the question type. The output unit outputs a search result based on the keyword for specifying the question object, in the display mode of the output.